A real-time multiagent wide-area stabilizing control framework for power system transient stability enhancement

In this paper, the design of a network of real-time close-loop wide-area decentralized power system stabilizers (WD-PSSs) is investigated. In this approach, real-time wide-area measurement data are processed and utilized to design a set of stability agents based on the Reinforcement Learning (RL) method and the multiagent system theory. Recent technological advances in wide-area measurement system (WAMS) make the use of remote signals possible in designing power system controllers. The proposed stability agents are decentralized and autonomous, but they are able to cooperate to fulfill the design objectives. The main design objective is to damp power system oscillations quickly after severe disturbances. This paper describes the developed framework and different challenges in designing such a network and their solutions. Case studies using a four-machine power system model are provided to illustrate the performance of the proposed approach.